A workflow for finding words that text-to-speech systems may pronounce incorrectly and preparing corrected scripts. Text-to-speech, or TTS, turns written text into spoken audio.

Use it to identify pronunciation risks, agree on corrected pronunciations with previews, and produce scripts ready for narration.

It helps prevent mistakes with names, brands, and unfamiliar words that may sound wrong in the finished narration. It uses audio previews because pronunciation depends on surrounding words.

phoneticize — Skill for Claude Code and Codex by leynos

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add leynos/visual-storytelling-skills --skill phoneticize

Clone the repo

git clone --depth 1 https://github.com/leynos/visual-storytelling-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leynos/visual-storytelling-skills/phoneticize/github.svg)](https://agentmods.dev/skills/leynos/visual-storytelling-skills/phoneticize)

Your own site

<a href="https://agentmods.dev/skills/leynos/visual-storytelling-skills/phoneticize"><img src="https://agentmods.dev/badge/skills/leynos/visual-storytelling-skills/phoneticize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/leynos/visual-storytelling-skills/phoneticize"><img src="https://agentmods.dev/badge/skills/leynos/visual-storytelling-skills/phoneticize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,652 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00225	$0.02652
Opus 5.5	$0.00090	$0.01061
Sonnet 5.5	$0.00045	$0.00530
Haiku 4.5	$0.00022	$0.00265

Measured 2mo ago against content hash 897545d4de61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phoneticize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/extract_candidates.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/phoneticize/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phoneticize — TTS pronunciation prep

A workflow for identifying pronunciation hazards in a TTS script, agreeing phonetic renderings with the user via audio previews, and emitting a phoneticized script ready for narration.

Read first

Reference	When to read	Path
Detection heuristics	Before Phase 1 — patterns that find candidates and how to combine them	`references/detection-heuristics.md`
Respelling conventions	Before Phase 2 — how to write phonetic respellings that Eleven v3 actually obeys	`references/respelling-conventions.md`
Eleven v3 format notes	Before Phase 3 and Phase 5 — what the engine accepts and silently ignores	`references/eleven-v3-notes.md`

Governing principles

Preview the fragment, not the word. TTS prosody depends on surrounding context. A respelling that sounds right in isolation collapses inside a sentence. Render fragments throughout.
Respelling is the primary output, not SSML. Eleven v3 silently drops <phoneme> tags (see references/eleven-v3-notes.md). Inline respelling — Siobhán → shi-VAWN directly in the prose — is what actually changes the model's output. IPA goes in the table for archival precision; respelling goes in the script.
Mark uncertainty, never guess. A wrong respelling shipped with confidence is worse than an explicit ? the user resolves. When the pronunciation isn't obvious, ask.
Stable IDs across iterations. Each candidate gets a row ID (P01, P02, …) on first pass and keeps it for the lifetime of the table. The user references rows by ID; regenerate only the rows that changed.
Render once, accept once. Never re-render an accepted row — it wastes Higgsfield calls and the user will assume something broke when the audio differs subtly between takes.

Phase 1 — Scan

Combine the regex helper with semantic reading. Neither alone catches everything: regex misses ordinary-looking words with non-obvious pronunciation (Worcester, Featherstonehaugh), and an LLM scan alone will miss tokens deep in long scripts.

Read the full file on GitHub · 255 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 255 lines · 225 tokens per session scan A 897545d4de61

Subscribe to this mod's changes

phoneticize is a skill published in the GitHub repository leynos/visual-storytelling-skills (9 stars, last pushed 29d ago), licensed ISC. It adds 225 tokens to every session and 2,652 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media agent-skills ai-image-generation ai-video-generation claude-skills higgsfield-ai nanobanana

phoneticize next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
phoneticizeleynos/visual-storytelling-skills	Skill	9	29d ago	ISC	A	225	Claude Code, Codex
wavespeedWaveSpeedAI/wavespeed-cli	Skill	26	2d ago	MIT	A	81	Claude Code, Codex
imagesmixs/visual-skills	Skill	632	2d ago	CC-BY-4.0	A	163	Claude Code
ai-hive-simulate-ali-abdaalwubin1836/ai-hive-agent-skills	Skill	23	28d ago	MIT	A	321	Codex
ai-hive-simulate-aravind-srinivaswubin1836/ai-hive-agent-skills	Skill	23	28d ago	MIT	A	338	Codex
ai-hive-simulate-baoyu-xpwubin1836/ai-hive-agent-skills	Skill	23	28d ago	MIT	A	305	Codex
ai-hive-simulate-berryxia-aiwubin1836/ai-hive-agent-skills	Skill	23	28d ago	MIT	A	319	Codex